© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 105319
    Prev
    Next
    INDEX
    Explanations

    college university

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trump
    -0.07
     Murdoch
    -0.06
    559
    -0.06
     Für
    -0.06
    755
    -0.06
    660
    -0.06
     accommod
    -0.06
     AMC
    -0.06
    .pre
    -0.06
    게시
    -0.06
    POSITIVE LOGITS
     dolay
    0.07
    erval
    0.07
    ("${
    0.07
     Longer
    0.06
     lượt
    0.06
     відб
    0.06
     ));↵
    0.06
     stdClass
    0.06
     Tradable
    0.06
     <>↵
    0.06
    Activations Density 0.019%

    No Known Activations